NewHow we catch a seller listing the wrong model, and refund you if one does.
UberLLM
Z.ai logo

How do I use GLM 5.3 Flash in OpenCode?

z-ai/glm-5.3-flash

OpenCode reaches GLM 5.3 Flash through the OpenAI-compatible chat address of UberLLM. In ~/.config/opencode/opencode.json, add a provider named uberllm that uses the @ai-sdk/openai-compatible package with baseURL set to https://api.uberllm.dev/v1, list z-ai/glm-5.3-flash under its models, put your UberLLM key in the UBERLLM_API_KEY environment variable, then pick uberllm/z-ai/glm-5.3-flash with /models. The limit numbers are the context size and the largest reply of GLM 5.3 Flash; OpenCode uses them to know when to compact a long session.

json
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "uberllm": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "UberLLM",
      "options": {
        "baseURL": "https://api.uberllm.dev/v1",
        "apiKey": "{env:UBERLLM_API_KEY}"
      },
      "models": {
        "z-ai/glm-5.3-flash": {
          "name": "GLM 5.3 Flash",
          "limit": {
            "context": 1048576,
            "output": 131072
          }
        }
      }
    }
  },
  "model": "uberllm/z-ai/glm-5.3-flash"
}

OpenCode calls: OpenAI chat completions https://api.uberllm.dev/v1/chat/completions · Full OpenCode guide

Replace ull_your_key with your UberLLM API key. One key works in every tool and for every model.

By API, GLM 5.3 Flash answers on three addresses with the same UberLLM key and the model id z-ai/glm-5.3-flash: OpenAI chat completions at https://api.uberllm.dev/v1/chat/completions, the OpenAI Responses API at https://api.uberllm.dev/v1/responses and the Anthropic Messages API at https://api.uberllm.dev/v1/messages.

How much does the GLM 5.3 Flash API cost?

On November 19, 2026, GLM 5.3 Flash costs $0.00168 per million input tokens and $0.00415 per million output tokens through UberLLM, 98.9% below its list price of $0.15 and $0.50. 242 sellers on the market can serve it. In the 7 days before, half of its 14,607 streamed requests got their first token within 11.0 seconds, with a typical prompt of 154,624 tokens. It reads up to 1,048,576 tokens of context. UberLLM adds no fee to these prices, and a request that fails is not billed.

Prices as of 09:00 UTC.

GLM 5.3 Flash in other tools

Other models in OpenCode